跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 魏怡如
Yi-Ru Wei
論文名稱： 評論內容屬性與評論幫助性關係之研究
Important factors that affect perceived reviews helpfulness
指導教授： 陳炫碩
Shiuann-Shuoh Chen
口試委員:
學位類別： 碩士
Master
系所名稱： 管理學院 - 企業管理學系
Department of Business Administration
論文出版年： 2021
畢業學年度： 110
語文別： 中文
論文頁數： 41
中文關鍵詞： 情感分析 、文字探勘 、經驗性商品 、搜尋性商品
外文關鍵詞： sentiment analysis, text mining, search goods, experience goods
相關次數： 點閱：10  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 隨著科技的發展以及網路購物的普及，線上評論對於電商領域可謂說是越
    來越重要，有學者認為評論對於消費者的影響甚至會比賣家提供的資訊還大。
    評論不僅可以讓消費者了解到產品的品質，也可以提升消費者對於平台的黏著
    度。
    過去有文獻探討評論內容的廣度、情緒對於評論幫助性的影響，本研究更
    深入探討當消費者閱讀經驗性商品與搜尋性商品評論時，覺得有幫助的評論是
    否會不一樣。本篇研究使用文字探勘的手法分析評論的情緒以及評論的廣度，
    以及分析消費者閱讀不同產品類別時吸收資訊的方式，進而提供平台營運上的
    建議。

    Online reviews have become more and more important in Ecommerce industry and are thought to be more helpful than seller generated information. Moreover, reviews have been shown to improve customers’ perception of the product quality, and can also increase customers’ stickiness to the website.
    With these benefits of review, understanding the important attributes of a helpful review let the Ecommerce be able to identify and promote more informative content, to develop encouraging content, and ultimately increase customers’ stickiness and user satisfaction to the website.
    Previous researches have analyzed how review breadth and review sentiment affects perceived review helpfulness; moreover, there are also some researches mention the differences of information processing method between search goods and experience when reading reviews.
    Therefore, the study utilizes text mining technique to analyze how product types affect the perceived review helpfulness. Positive and negative emotion is calculated using VADER, and this study also conduct BERTopics to calculate the topic distribution for each review. Finally, this paper discover the different information processing method between search goods and experience goods, and hence give the suggestion to Ecommerce platform base on the finding.

    中文摘要 .................................................... I ABSTRACT................................................... II 目錄 TABLE OF CONTENTS..................................... IV 表目錄 LIST OF TABLES........................................ V 圖目錄 LIST OF FIGURES..................................... VI I.INTRODUCTION ............................................ 1 1.1 BACKGROUND AND MOTIVATION.............................. 1 LITERATURE REVIEW.......................................... 3 2.1 NEGATIVITY BIAS ....................................... 3 2.2 ANGER REVIEW .......................................... 3 2.3 PRODUCT TYPES: EXPERIENCE GOODS AND SEARCH GOODS....... 4 2.4 THEORETICAL FRAMEWORK ................................. 5 III. EXPERIMENT ........................................... 6 3.1 DATA COLLECTION ....................................... 6 3.2 DATA EXTRACTION........................................ 7 3.2.1 Data extraction based on product types............... 7 3.2.2 Filtering out reviews with at least one vote ........ 8 3.3 TEXT PRE-PROCESSING ................................... 9 3.4 VARIABLE CONSTRUCTION ................................. 10 3.4.1 Sentiment Analysis................................... 10 3.4.2 Topic Comprehensiveness ............................. 12 3.4.3 Detailed Explanation................................. 16 3.4.4 Extreme Star Rating ................................. 18 3.4.5 Number of Words...................................... 18 3.4.6 Number of Days ...................................... 19 3.4.7 Review Helpfulness .................................. 19 IV. DATA ANALYSIS AND RESULT .............................. 20 4.1 VARIABLE DESCRIPTION .................................. 20 4.2 CORRELATION MATRIX .................................... 22 4.3 RESULT ................................................ 24 4.3.1 The general effect of OLS result .................... 25 4.3.2 OLS analysis for Product Types ...................... 25 V. CONCLUSION ............................................. 27 5.1 THEORETICAL IMPLICATIONS .............................. 27 5.2 PRACTICAL IMPLICATIONS ................................ 27 VI. REFERENCE ............................................. 28

    [1] Barbara Bickart; Robert M. Schindler (2001). Internet forums as influential sources of consumer information. 15(3), 31–40
    [2] Shin, D., He, S., Lee, G. M., Whinston, A. B., Cetintas, S., & Lee, K. (2019). Enhancing social media analysis with visual data analytics: A deep learning approach.
    [3] Willemsen, L. M., Neijens, P. C., Bronner, F., & de Ridder, J. A. (2011). “Highly Recommended!” The Content Characteristics and Perceived Usefulness of Online Consumer Reviews. In Journal of Computer- Mediated Communication (Vol. 17, Issue 1, pp. 19–38). Oxford University Press (OUP).
    [4] Chen, P.-Y., Dhanasobhon, S., & Smith, M. D. (2008). All Reviews are Not Created Equal: The Disaggregate Impact of Reviews and Reviewers at Amazon.Com. In SSRN Electronic Journal.
    [5] Mudambi, & Schuff. (2010). Research Note: What Makes a Helpful Online Review? A Study of Customer Reviews on Amazon.com. MIS Quarterly (Vol. 34, Issue 1, p. 185).
    [6] Chevalier, J. A., & Mayzlin, D. (2006). The Effect of Word of Mouth on Sales: Online Book Reviews. In Journal of Marketing Research (Vol. 43, Issue 3, pp. 345–354).
    [7] Tripathi, P., Vishwakarma, S. Kr., & Lala, A. (2015). Sentiment Analysis of English Tweets Using Rapid Miner. In 2015 International Conference on Computational Intelligence and Communication Networks (CICN).
    [8] Guo, Y., Barnes, S. J., & Jia, Q. (2017). Mining meaning from online ratings and reviews: Tourist satisfaction analysis using latent dirichlet allocation. Tourism Management, 59, 467-483.
    [9] Jabbar, A., Iqbal, S., Tamimy, M. I., Hussain, S., & Akhunzada, A. (2020). Empirical evaluation and study of text stemming algorithms. Artificial Intelligence Review, 53(8), 5559-5588.
    [10] Kahneman, D., & Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk. In Econometrica (Vol. 47, Issue 2, p. 263)
    [11] Hickman, L., Thapa, S., Tay, L., Cao, M., & Srinivasan, P. (2020). Text preprocessing for text mining in organizational research: Review and recommendations.
    [12] Balakrishnan, V., & Ethel, L.-Y. (2014). Stemming and Lemmatization: A Comparison of Retrieval Performances. In Lecture Notes on Software
    Engineering (Vol. 2, Issue 3, pp. 262–267)
    [13] Cheung, M. Y., Luo, C., Sia, C. L., & Chen, H. (2009). Credibility of Electronic
    Word-of-Mouth: Informational and Normative Determinants of On-line Consumer Recommendations. In International Journal of Electronic Commerce (Vol. 13, Issue 4, pp. 9–38).
    [14] Skowronski, J. J., & Carlston, D. E. (1989). Negativity and extremity biases in impression formation: A review of explanations. In Psychological Bulletin (Vol. 105, Issue 1, pp. 131–142). American Psychological Association (APA).
    [15] BERTopic: Neural topic modeling with a class-based TF-IDF procedure
    [16] Jianmo Ni, Jiacheng Li, Julian McAuley (2019) Empirical Methods in
    Natural Language Processing (EMNLP)

    QR CODE
    :::